Assignment 1: Looking at Animation Papers

by Mike Gleicher on January 14, 2011 · 5 comments

in Assignments

The goal of this assignment is to give you a sense of what an animation paper is like, and also to get some sense of what people are interested in. It’s also a bit of social engineering to get everyone talking about animation stuff.

Note: you are not supposed to read all the details of the paper. You are just going to read over the front parts, and skim over the rest.

Start by looking over my notes on graphics/animation papers for this class.

Each person will do this exercise for 4/5 papers – I will assign each person 2 papers, and then you will pick 2 more from the list below. When you are looking through the list of the papers at the various conferences (to find ones on the list), see if a paper sticks out that really interests you. If you find one, add it to your list of papers.

4 papers is (intentionally) too many to read. And the papers are probably things that you don’t have the technical background (yet) to understand the details. But the goal is to get you to learn to find the gist quickly, and to see what is interesting to you.

For each paper you look at, you need to:

  1. Identify “The Sentence.” If you really can’t find it, try to create it yourself. My guess is, that for most SIGGRAPH/SCA papers, you will find “The Sentence.” (note: you should copy the sentence out of the paper, or be explicit that you are making it up – or say where the sentence appears in the paper.)
  2. State “The Problem”.” Again, the authors should make this easy. But you should be able to state quickly what the problem the paper deals with is. It could very well be that this is really similar to the answer to #1.
  3. See if you can state the key idea of the paper in a sentence or two. You might not understand the key idea (as it might involve techniques that you don’t know yet).
  4. Describe what this paper lets you do. This has two parts: first, identify the cool demonstration of what the method does – what is the killer example? (hint: go to the author’s web site and watch the video!). Second: try to figure out what the ideas/techniques in the paper might be good for.
  5. Did you find any other materials? (videos? talk slides? extra explanations?)

Note that I did not ask you to write a summary of the paper! In fact, I did not even ask you to read the whole papers. You do need to find the paper (shouldn’t be hard), and look around for some extra information. And write 6 or so sentences (that answer 6 questions – since Q4 has 2 parts). Please use the paper title as the title of your post, be explicit about which part of the post is answering which question, and whether you were assigned the paper, chose it from the list, or chose it despite not being on the list.

I wrote an example for one of the papers.

For each paper, write the answers to the questions as a posting to this blog, in the category “Assignment 1”. Each paper that you answer the questions for should be a separate post. Make sure you have done all of your comments before 6pm on Sunday, 1/23 so that I have a chance to read over them before class (and approve them so others can read them).

Be prepared to talk about the papers that you looked at in class on Monday, 1/24. You might want to print out what you wrote as answers to those 5 questions and bring them with you.

A List of Some Animation Papers from the past year or so…

Here is a list of papers chosen from recent conferences. In addition to the two papers you were assigned, you should pick 2 more from this list. You should be able to find the paper on the web (for example, in the ACM Digital Library), but you might also try looking at the “Graphics Papers on the Web” Resource (check this out – you will find it really valuable).


  • Example-based Facial Rigging (AB)
  • Face poser: Interactive modeling of 3D facial expressions using facial priors (DA)
  • Spatial Relationship Preserving Character Motion Adaptation (RB)
  • Interactive Generation of Human Animation with Deformable Motion Models (MC)
  • VideoMocap: Modeling Physically Realistic Human Motion from Monocular Video Sequences (SaGa)
  • Programmable Motion Effects (DC)
  • 2.5D Cartoon Models (AB)
  • Robust Physics-Based Locomotion Using Low-Dimensional Planning (CV)
  • Optimal Feedback Control for Character Animation Using an Abstract Model (DG)
  • Seeing is Believing: Body Motion Dominates in Multisensory Conversations (SuGh)
  • Stable Spaces for Real-time Clothing (RS)
  • Example-Based Wrinkle Synthesis for Clothing Animation (NM)
  • A Deformation Transformer for Real-Time Cloth Animation (SA)
  • Learning Behavior Styles with Inverse Reinforcement Learning (JH)
  • Gesture Controllers (AM)

SIGGRAPH Asia 2010

  • Motion Fields for Interactive Character Animation (DA)
  • Stable Inverse Dynamic Curves (LW)
  • Video-based Reconstruction of Animatable Human Characters (RB,AB)
  • MovieReshape: Tracking and Reshaping of Humans in Videos (MC)
  • Animation Wrinkling: Augmenting Coarse Cloth Simulations With Realistic-Looking Wrinkles (SaGa)
  • Piles of Objects (DA)

Eurographics 2010

  • Multi-Scale Geometry Interpolation (SA)
  • Fast and Efficient Skinning of Animated Meshes (SuGh)
  • Bidirectional Search for Interactive Motion Synthesis (XZ)
  • Synthesis of Responsive Motion Using a Dynamic Model
  • Human Motion Synthesis with Optimization-based Graphs
  • The Virtual Director: a Correlation-Based Online Viewing of Human Motion (DG)
  • BetweenIT: An Interactive Tool for Tight Inbetweening (NM)

SCA 2010

  • Fast Local and Global Similarity Searches in Large Motion Capture Databases (DC)
  • Modeling Style and Variation in Human Motion (AM)
  • Augmenting Hand Animation with Three-Dimensional Secondary Motion (CV)
  • A Real-time Cinematography System for 3D Environments (RS)
  • Shortest Paths with Arbitrary Clearance from Navigation Meshes (LW)
  • Animating Non-Humanoid Characters with Human Motion Data (JH)
  • Point Cloud Glue: Constraining simulations using the Procrustes transform (XZ)

SCA 2009

  • Face/Off: Live Facial Puppetry
  • Efficient and Robust Annotation of Motion Capture Data
  • Interactive Synthesis of Human-Object Interaction
  • Leveraging the Talent of Hand Animators to Create Three-Dimensional Animation
  • Interactive Editing of Motion Style Using Drives and Correlations
  • Pose-Timeline for Propagating Motion Edits
  • Style Learning and Transferring for Facial Animation Editing
  • Statistical Simulation of Rigid Bodies
  • Real-Time Deformation and Fracture in a Game Environment


rsawtell January 23, 2011 at 2:08 pm

Stable Spaces for Real-time Clothing

1. We present a technique for learning clothing models that enables
the simultaneous animation of thousands of detailed garments in
real-time. [first sentence of abstract]

2. Modern cloth simulation is really nice, but expensive. Would like a compromise with low dimensional models but keep expressiveness of cloth discretization.

3. Observe cloth behavior under physical simulation to learn a simpler (non-physically based) proxy model. This model will generally behave well and is much less computationally expensive.

4. This paper lets you realistically simulate lots of cloth at the same time. Claimed naive approach (there is room for improvement) gave 3x faster result than Maya Cloth, rendered 170 real time clothing articles, or 1000 without rendering.

5. Reference Video:

gleicher January 23, 2011 at 2:11 pm

Your responses for this assignment should not be a comment – it should be a posting. To do that, you need to sign in, and pick “new post” either in the right hand menu, or from the dashboard.

rsawtell January 23, 2011 at 2:50 pm

A Real-time Cinematography System for 3D Environments

1. We propose a fully automated system that
constructs a cinematically expressive movie in real-time
from a flow of low-level narrative elements generated as the
environment evolves.

2. Traditional methods only look at isolated aspects of cinematography and do not allow for style variations.

3. Select narrative elements with a narrative engine, compose selected elements with analysis of visibility of key targets into director volumes, use a customizeable set of filters to select appropriate volumes, compute transitions between volumes.

4. This paper lets you automate all the cinematography components in real time while allowing for differences in director styling.

5. Slideshow:

{ 2 trackbacks }

Previous post:

Next post: